Add vector search to experimental page

pages/database-management/experimental-features.mdx

@@ -18,25 +18,75 @@ encouraged to thoroughly test the experimental features in your environment.
 
 To enable multiple experimental features in Memgraph, you need to use the
 `--experimental-enabled` flag followed by the name of the feature. Here's how
-you can enable the `text-search`
-feature at the same time:
+you can enable the `vector-search` and `text-search` features at the same time: 
 
-`--experimental-enabled=text-search`
+`--experimental-enabled=vector-search,text-search`
 
 If you already have a Memgraph instance with an experimental feature enabled,
 and you want to add another one, you will need to restart Memgraph. Ensure that
 all the necessary flags are enabled during the restart.
 
+Some experimental features, such as `vector-search`, require
+`--experimental-config` flag for proper configuration.
+
 </Callout>
 
 ## Experimental features list
 
+### Vector Search
+- **Description**: Enables approximate nearest neighbor searches in Memgraph by
+  leveraging the [HNSW](https://arxiv.org/abs/1603.09320) algorithm to index
+  node properties as vectors. This feature supports various similarity metrics,
+  enabling efficient retrieval of nodes based on vector similarity. While the
+  database itself can operate at any configured isolation level, the vector
+  index specifically functions at the `READ UNCOMMITTED` isolation level.
+  **This means that changes to the index made by uncommitted transactions are
+  immediately visible to other transactions, regardless of the database's
+  isolation level!**
+- **Status**: Experimental. The vector search feature is still under
+  development and not fully integrated with other Memgraph functionalities.
+  Unlike other index types, it currently lacks support for durability,
+  replication, and multi-tenancy. Additionally, vector indexes must be created
+  using the `--experimental-config` flag, rather than through Cypher queries
+  like other indexes. Although durability, replication, and multi-tenancy are
+  not yet supported, you can work around these limitations by ensuring that
+  every database instance (main or replica) is started with the same
+  `--experimental-config` flag. This ensures expected behavior for these
+  features across instances. Vector search is an actively developed feature,
+  and we are continuously working on improving its capabilities. At the time of
+  writing, 2024-11-27, the plan is to make feature stable at the time of the
+  next release which is 2025-01-29.
+- **Usage**: Enable the feature using the flag
+  `--experimental-enabled=vector-search`. Configure the feature using
+  `--experimental-config`. For example:
+  ```shell
+  --experimental-config='
+  {
+    "vector-search": {
+      "index_name": {
+        "label": "Node",
+        "property": "vector",
+        "dimension": 2,
+        "capacity": 1000,
+        "metric": "cos",
+        "scalar": "f32",
+        "resize_coefficient": 2
+      }
+    }
+  }
+  '
+  ```
+  Keep in mind that both flags are required and the configuration requires the
+  following mandatory fields: `label`, `property`, `dimension` and `capacity`.
+- **Documentation**: For more details, visit the [vector search
+  page](/querying/vector-search).
+
 ### Text Search
 - **Description**: Enables finding nodes based on property values within
   Memgraph, supporting both literal and regex searches, and the concept of
   aggregation. It is not guaranteed to work correctly in use cases involving
   concurrent transactions and replication.
-- **Status**: Experimental. Provides text search functionalities but is not
+- **Status**: Early experimental. Provides text search functionalities but is not
   guaranteed to work correctly in use cases involving concurrent transactions
   and replication. There are no short-term plans to improve text-search
   capabilities. If you are interested in improvements, please contact us on

pages/querying/_meta.json

@@ -8,6 +8,7 @@
   "expressions": "Expressions",
   "schema": "Schema",
   "text-search": "Text search",
+  "vector-search": "Vector search",
   "time-to-live": "Time to live",
   "query-plan": "Query plan",
   "exploring-datasets": "Exploring datasets"

pages/querying/vector-search.mdx

@@ -0,0 +1,78 @@
+---
+title: Vector search
+description: Learn how to use vector search and manage vector indices in Memgraph.
+---
+
+import { Callout } from 'nextra/components'
+
+# Vector search
+
+The vector search is currently an experimental feature. For the exact status
+please visit the [experimental
+page](/database-management/experimental-features). To enable the feature use
+the following `--experimental-enabled=vector-search`. To configure the feature
+use `--experimental-config`. For example:
+```shell
+--experimental-config=
+'
+{
+  "vector-search": {
+    "index_name": {
+      "label": "Node",
+      "property": "vector",
+      "dimension": 2,
+      "capacity": 1000,
+      "metric": "cos",
+      "scalar": "f32",
+      "resize_coefficient": 2,
+    }
+  }
+}
+'
+```
+Keep in mind that both flags are required and the configuration requires the
+following mandatory fields: `label`, `property`, `dimension` and `capacity`.
+
+### Metric Kinds
+
+The following table lists the supported metric kinds for vector search. These
+metrics determine how distances between vectors are calculated. Default type
+for the metric is `l2sq`.
+
+| Metric      | Description                                          |
+|-------------|------------------------------------------------------|
+| `ip`        | Inner product (dot product).                         |
+| `cos`       | Cosine similarity.                                   |
+| `l2sq`      | Squared Euclidean distance.                          |
+| `pearson`   | Pearson correlation coefficient.                     |
+| `haversine` | Haversine distance (suitable for geographic data).   |
+| `divergence`| A divergence-based metric.                           |
+| `hamming`   | Hamming distance.                                    |
+| `tanimoto`  | Tanimoto coefficient.                                |
+| `sorensen`  | Sørensen-Dice coefficient.                           |
+| `jaccard`   | Jaccard index.                                       |
+
+### Scalar Kinds
+
+Scalar kinds define the data type of each vector element. Default type for the
+metric is `f32`.
+
+| Scalar    | Description                                            |
+|-----------|--------------------------------------------------------|
+| `b1x8`    | Binary format (1 bit per element, stored in 8-bit chunks). |
+| `u40`     | Unsigned 40-bit integer.                               |
+| `uuid`    | Universally unique identifier (UUID).                  |
+| `bf16`    | 16-bit floating point (bfloat16).                      |
+| `f64`     | 64-bit floating point (double).                        |
+| `f32`     | 32-bit floating point (float).                         |
+| `f16`     | 16-bit floating point.                                 |
+| `f8`      | 8-bit floating point.                                  |
+| `u64`     | 64-bit unsigned integer.                               |
+| `u32`     | 32-bit unsigned integer.                               |
+| `u16`     | 16-bit unsigned integer.                               |
+| `u8`      | 8-bit unsigned integer.                                |
+| `i64`     | 64-bit signed integer.                                 |
+| `i32`     | 32-bit signed integer.                                 |
+| `i16`     | 16-bit signed integer.                                 |
+| `i8`      | 8-bit signed integer.                                  |
+